LlamaParse Data Sources API
The Data Sources API from LlamaParse — 2 operation(s) for data sources.
OpenAPI Specification
openapi: 3.0.3
info:
title: Llama Platform Agent Data Data Sources API
version: 0.1.0
tags:
- name: Data Sources
paths:
/api/v1/data-sources:
get:
tags:
- Data Sources
summary: List Data Sources
description: 'List data sources for a given project.
If project_id is not provided, uses the default project.'
operationId: list_data_sources_api_v1_data_sources_get
security:
- HTTPBearer: []
parameters:
- name: project_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Project Id
- name: organization_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Organization Id
- name: session
in: cookie
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Session
responses:
'200':
description: Successful Response
content:
application/json:
schema:
type: array
items:
$ref: '#/components/schemas/DataSource'
title: Response List Data Sources Api V1 Data Sources Get
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
post:
tags:
- Data Sources
summary: Create Data Source
description: Create a new data source.
operationId: create_data_source_api_v1_data_sources_post
security:
- HTTPBearer: []
parameters:
- name: project_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Project Id
- name: organization_id
in: query
required: false
schema:
anyOf:
- type: string
format: uuid
- type: 'null'
title: Organization Id
- name: session
in: cookie
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Session
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/DataSourceCreate'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/DataSource'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
/api/v1/data-sources/{data_source_id}:
get:
tags:
- Data Sources
summary: Get Data Source
description: Get a data source by ID.
operationId: get_data_source_api_v1_data_sources__data_source_id__get
security:
- HTTPBearer: []
parameters:
- name: data_source_id
in: path
required: true
schema:
type: string
format: uuid
title: Data Source Id
- name: session
in: cookie
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Session
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/DataSource'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
put:
tags:
- Data Sources
summary: Update Data Source
description: Update a data source by ID.
operationId: update_data_source_api_v1_data_sources__data_source_id__put
security:
- HTTPBearer: []
parameters:
- name: data_source_id
in: path
required: true
schema:
type: string
format: uuid
title: Data Source Id
- name: session
in: cookie
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Session
requestBody:
required: true
content:
application/json:
schema:
$ref: '#/components/schemas/DataSourceUpdate'
responses:
'200':
description: Successful Response
content:
application/json:
schema:
$ref: '#/components/schemas/DataSource'
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
delete:
tags:
- Data Sources
summary: Delete Data Source
description: Delete a data source by ID.
operationId: delete_data_source_api_v1_data_sources__data_source_id__delete
security:
- HTTPBearer: []
parameters:
- name: data_source_id
in: path
required: true
schema:
type: string
format: uuid
title: Data Source Id
- name: session
in: cookie
required: false
schema:
anyOf:
- type: string
- type: 'null'
title: Session
responses:
'204':
description: Successful Response
'422':
description: Validation Error
content:
application/json:
schema:
$ref: '#/components/schemas/HTTPValidationError'
components:
schemas:
ConfigurableDataSourceNames:
type: string
enum:
- S3
- AZURE_STORAGE_BLOB
- GOOGLE_DRIVE
- MICROSOFT_ONEDRIVE
- MICROSOFT_SHAREPOINT
- SLACK
- NOTION_PAGE
- CONFLUENCE
- JIRA
- JIRA_V2
- BOX
title: ConfigurableDataSourceNames
CloudGoogleDriveDataSource:
properties:
supports_access_control:
type: boolean
title: Supports Access Control
default: false
folder_id:
type: string
title: Folder Id
description: The ID of the Google Drive folder to read from.
service_account_key:
anyOf:
- additionalProperties:
type: string
type: object
description: A dictionary containing secret values
- type: 'null'
title: Service Account Key
description: The service account key JSON to use for authentication.
class_name:
type: string
title: Class Name
default: CloudGoogleDriveDataSource
type: object
required:
- folder_id
title: CloudGoogleDriveDataSource
DataSource:
properties:
id:
type: string
format: uuid
title: Id
description: Unique identifier
created_at:
anyOf:
- type: string
format: date-time
- type: 'null'
title: Created At
description: Creation datetime
updated_at:
anyOf:
- type: string
format: date-time
- type: 'null'
title: Updated At
description: Update datetime
name:
type: string
title: Name
description: The name of the data source.
source_type:
$ref: '#/components/schemas/ConfigurableDataSourceNames'
custom_metadata:
anyOf:
- additionalProperties:
anyOf:
- additionalProperties: true
type: object
- items: {}
type: array
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
type: object
- type: 'null'
title: Custom Metadata
description: Custom metadata that will be present on all data loaded from the data source
component:
anyOf:
- additionalProperties: true
type: object
- $ref: '#/components/schemas/CloudS3DataSource'
- $ref: '#/components/schemas/CloudAzStorageBlobDataSource'
- $ref: '#/components/schemas/CloudGoogleDriveDataSource'
- $ref: '#/components/schemas/CloudOneDriveDataSource'
- $ref: '#/components/schemas/CloudSharepointDataSource'
- $ref: '#/components/schemas/CloudSlackDataSource'
- $ref: '#/components/schemas/CloudNotionPageDataSource'
- $ref: '#/components/schemas/CloudConfluenceDataSource'
- $ref: '#/components/schemas/CloudJiraDataSource'
- $ref: '#/components/schemas/CloudJiraDataSourceV2'
- $ref: '#/components/schemas/CloudBoxDataSource'
title: DataSourceCreateComponent
description: Component that implements the data source
version_metadata:
anyOf:
- $ref: '#/components/schemas/DataSourceReaderVersionMetadata'
- type: 'null'
description: Version metadata for the data source
project_id:
type: string
format: uuid
title: Project Id
type: object
required:
- id
- name
- source_type
- component
- project_id
title: DataSource
description: Schema for a data source.
HTTPValidationError:
properties:
detail:
items:
$ref: '#/components/schemas/ValidationError'
type: array
title: Detail
type: object
title: HTTPValidationError
CloudJiraDataSource:
properties:
supports_access_control:
type: boolean
title: Supports Access Control
default: false
email:
anyOf:
- type: string
- type: 'null'
title: Email
description: The email address to use for authentication.
api_token:
anyOf:
- type: string
format: password
writeOnly: true
- type: 'null'
title: Api Token
description: The API/ Access Token used for Basic, PAT and OAuth2 authentication.
server_url:
anyOf:
- type: string
- type: 'null'
title: Server Url
description: The server url for Jira Cloud.
cloud_id:
anyOf:
- type: string
- type: 'null'
title: Cloud Id
description: The cloud ID, used in case of OAuth2.
authentication_mechanism:
type: string
title: Authentication Mechanism
description: Type of Authentication for connecting to Jira APIs.
query:
type: string
title: Query
description: JQL (Jira Query Language) query to search.
class_name:
type: string
title: Class Name
default: CloudJiraDataSource
type: object
required:
- authentication_mechanism
- query
title: CloudJiraDataSource
description: Cloud Jira Data Source integrating JiraReader.
BoxAuthMechanism:
type: string
enum:
- developer_token
- ccg
title: BoxAuthMechanism
FailureHandlingConfig:
properties:
skip_list_failures:
type: boolean
title: Skip List Failures
description: Whether to skip failed batches/lists and continue processing
default: false
type: object
title: FailureHandlingConfig
description: Configuration for handling different types of failures during data source processing.
CloudAzStorageBlobDataSource:
properties:
supports_access_control:
type: boolean
title: Supports Access Control
default: false
container_name:
type: string
title: Container Name
description: The name of the Azure Storage Blob container to read from.
account_url:
type: string
title: Account Url
description: The Azure Storage Blob account URL to use for authentication.
blob:
anyOf:
- type: string
- type: 'null'
title: Blob
description: The blob name to read from.
prefix:
anyOf:
- type: string
- type: 'null'
title: Prefix
description: The prefix of the Azure Storage Blob objects to read from.
account_name:
anyOf:
- type: string
- type: 'null'
title: Account Name
description: The Azure Storage Blob account name to use for authentication.
account_key:
anyOf:
- type: string
format: password
writeOnly: true
- type: 'null'
title: Account Key
description: The Azure Storage Blob account key to use for authentication.
tenant_id:
anyOf:
- type: string
- type: 'null'
title: Tenant Id
description: The Azure AD tenant ID to use for authentication.
client_id:
anyOf:
- type: string
- type: 'null'
title: Client Id
description: The Azure AD client ID to use for authentication.
client_secret:
anyOf:
- type: string
format: password
writeOnly: true
- type: 'null'
title: Client Secret
description: The Azure AD client secret to use for authentication.
class_name:
type: string
title: Class Name
default: CloudAzStorageBlobDataSource
type: object
required:
- container_name
- account_url
title: CloudAzStorageBlobDataSource
CloudConfluenceDataSource:
properties:
supports_access_control:
type: boolean
title: Supports Access Control
default: false
server_url:
type: string
title: Server Url
description: The server URL of the Confluence instance.
authentication_mechanism:
type: string
title: Authentication Mechanism
description: Type of Authentication for connecting to Confluence APIs.
user_name:
anyOf:
- type: string
- type: 'null'
title: User Name
description: The username to use for authentication.
api_token:
anyOf:
- type: string
format: password
writeOnly: true
- type: 'null'
title: Api Token
description: The API token to use for authentication.
space_key:
anyOf:
- type: string
- type: 'null'
title: Space Key
description: The space key to read from.
page_ids:
anyOf:
- type: string
- type: 'null'
title: Page Ids
description: The page IDs of the Confluence to read from.
cql:
anyOf:
- type: string
- type: 'null'
title: Cql
description: The CQL query to use for fetching pages.
label:
anyOf:
- type: string
- type: 'null'
title: Label
description: The label to use for fetching pages.
index_restricted_pages:
type: boolean
title: Index Restricted Pages
description: Whether to index restricted pages.
default: false
keep_markdown_format:
type: boolean
title: Keep Markdown Format
description: Whether to keep the markdown format.
failure_handling:
$ref: '#/components/schemas/FailureHandlingConfig'
description: "Configuration for handling failures during processing. Key-value object controlling failure handling behaviors.\n\nExample:\n{\n \"skip_list_failures\": true\n}\n\nCurrently supports:\n- skip_list_failures: Skip failed batches/lists and continue processing"
class_name:
type: string
title: Class Name
default: CloudConfluenceDataSource
type: object
required:
- authentication_mechanism
- server_url
title: CloudConfluenceDataSource
ValidationError:
properties:
loc:
items:
anyOf:
- type: string
- type: integer
type: array
title: Location
msg:
type: string
title: Message
type:
type: string
title: Error Type
input:
title: Input
ctx:
type: object
title: Context
type: object
required:
- loc
- msg
- type
title: ValidationError
CloudOneDriveDataSource:
properties:
supports_access_control:
type: boolean
const: true
title: Supports Access Control
default: true
user_principal_name:
type: string
title: User Principal Name
description: The user principal name to use for authentication.
folder_path:
anyOf:
- type: string
- type: 'null'
title: Folder Path
description: The path of the OneDrive folder to read from.
folder_id:
anyOf:
- type: string
- type: 'null'
title: Folder Id
description: The ID of the OneDrive folder to read from.
client_id:
type: string
title: Client Id
description: The client ID to use for authentication.
client_secret:
type: string
format: password
title: Client Secret
description: The client secret to use for authentication.
writeOnly: true
tenant_id:
type: string
title: Tenant Id
description: The tenant ID to use for authentication.
required_exts:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Required Exts
description: The list of required file extensions.
class_name:
type: string
title: Class Name
default: CloudOneDriveDataSource
type: object
required:
- user_principal_name
- client_id
- client_secret
- tenant_id
title: CloudOneDriveDataSource
CloudS3DataSource:
properties:
supports_access_control:
type: boolean
title: Supports Access Control
default: false
bucket:
type: string
title: Bucket
description: The name of the S3 bucket to read from.
prefix:
anyOf:
- type: string
- type: 'null'
title: Prefix
description: The prefix of the S3 objects to read from.
regex_pattern:
anyOf:
- type: string
- type: 'null'
title: Regex Pattern
description: The regex pattern to filter S3 objects. Must be a valid regex pattern.
aws_access_id:
anyOf:
- type: string
- type: 'null'
title: Aws Access Id
description: The AWS access ID to use for authentication.
aws_access_secret:
anyOf:
- type: string
format: password
writeOnly: true
- type: 'null'
title: Aws Access Secret
description: The AWS access secret to use for authentication.
s3_endpoint_url:
anyOf:
- type: string
- type: 'null'
title: S3 Endpoint Url
description: The S3 endpoint URL to use for authentication.
class_name:
type: string
title: Class Name
default: CloudS3DataSource
type: object
required:
- bucket
title: CloudS3DataSource
DataSourceUpdate:
properties:
name:
anyOf:
- type: string
- type: 'null'
title: Name
description: The name of the data source.
source_type:
$ref: '#/components/schemas/ConfigurableDataSourceNames'
custom_metadata:
anyOf:
- additionalProperties:
anyOf:
- additionalProperties: true
type: object
- items: {}
type: array
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
type: object
- type: 'null'
title: Custom Metadata
description: Custom metadata that will be present on all data loaded from the data source
component:
anyOf:
- additionalProperties: true
type: object
- $ref: '#/components/schemas/CloudS3DataSource'
- $ref: '#/components/schemas/CloudAzStorageBlobDataSource'
- $ref: '#/components/schemas/CloudGoogleDriveDataSource'
- $ref: '#/components/schemas/CloudOneDriveDataSource'
- $ref: '#/components/schemas/CloudSharepointDataSource'
- $ref: '#/components/schemas/CloudSlackDataSource'
- $ref: '#/components/schemas/CloudNotionPageDataSource'
- $ref: '#/components/schemas/CloudConfluenceDataSource'
- $ref: '#/components/schemas/CloudJiraDataSource'
- $ref: '#/components/schemas/CloudJiraDataSourceV2'
- $ref: '#/components/schemas/CloudBoxDataSource'
- type: 'null'
title: DataSourceUpdateComponent
description: Component that implements the data source
type: object
required:
- source_type
title: DataSourceUpdate
description: Schema for updating a data source.
DataSourceReaderVersionMetadata:
properties:
reader_version:
anyOf:
- type: string
enum:
- '1.0'
- '2.0'
- '2.1'
- type: 'null'
title: Reader Version
description: The version of the reader to use for this data source.
type: object
title: DataSourceReaderVersionMetadata
DataSourceCreate:
properties:
name:
type: string
title: Name
description: The name of the data source.
source_type:
$ref: '#/components/schemas/ConfigurableDataSourceNames'
custom_metadata:
anyOf:
- additionalProperties:
anyOf:
- additionalProperties: true
type: object
- items: {}
type: array
- type: string
- type: integer
- type: number
- type: boolean
- type: 'null'
type: object
- type: 'null'
title: Custom Metadata
description: Custom metadata that will be present on all data loaded from the data source
component:
anyOf:
- additionalProperties: true
type: object
- $ref: '#/components/schemas/CloudS3DataSource'
- $ref: '#/components/schemas/CloudAzStorageBlobDataSource'
- $ref: '#/components/schemas/CloudGoogleDriveDataSource'
- $ref: '#/components/schemas/CloudOneDriveDataSource'
- $ref: '#/components/schemas/CloudSharepointDataSource'
- $ref: '#/components/schemas/CloudSlackDataSource'
- $ref: '#/components/schemas/CloudNotionPageDataSource'
- $ref: '#/components/schemas/CloudConfluenceDataSource'
- $ref: '#/components/schemas/CloudJiraDataSource'
- $ref: '#/components/schemas/CloudJiraDataSourceV2'
- $ref: '#/components/schemas/CloudBoxDataSource'
title: DataSourceCreateComponent
description: Component that implements the data source
type: object
required:
- name
- source_type
- component
title: DataSourceCreate
description: Schema for creating a data source.
CloudBoxDataSource:
properties:
supports_access_control:
type: boolean
title: Supports Access Control
default: false
folder_id:
anyOf:
- type: string
- type: 'null'
title: Folder Id
description: The ID of the Box folder to read from.
authentication_mechanism:
$ref: '#/components/schemas/BoxAuthMechanism'
description: The type of authentication to use (Developer Token or CCG)
developer_token:
anyOf:
- type: string
format: password
writeOnly: true
- type: 'null'
title: Developer Token
description: Developer token for authentication if authentication_mechanism is 'developer_token'.
client_id:
anyOf:
- type: string
- type: 'null'
title: Client Id
description: Box API key used for identifying the application the user is authenticating with
client_secret:
anyOf:
- type: string
format: password
writeOnly: true
- type: 'null'
title: Client Secret
description: Box API secret used for making auth requests.
user_id:
anyOf:
- type: string
- type: 'null'
title: User Id
description: Box User ID, if provided authenticates as user.
enterprise_id:
anyOf:
- type: string
- type: 'null'
title: Enterprise Id
description: Box Enterprise ID, if provided authenticates as service.
class_name:
type: string
title: Class Name
default: CloudBoxDataSource
type: object
required:
- authentication_mechanism
title: CloudBoxDataSource
CloudNotionPageDataSource:
properties:
supports_access_control:
type: boolean
title: Supports Access Control
default: false
integration_token:
type: string
format: password
title: Integration Token
description: The integration token to use for authentication.
writeOnly: true
database_ids:
anyOf:
- type: string
- type: 'null'
title: Database Ids
description: The Notion Database Id to read content from.
page_ids:
anyOf:
- type: string
- type: 'null'
title: Page Ids
description: The Page ID's of the Notion to read from.
class_name:
type: string
title: Class Name
default: CloudNotionPageDataSource
type: object
required:
- integration_token
title: CloudNotionPageDataSource
CloudSharepointDataSource:
properties:
supports_access_control:
type: boolean
const: true
title: Supports Access Control
default: true
site_name:
anyOf:
- type: string
- type: 'null'
title: Site Name
description: The name of the SharePoint site to download from.
site_id:
anyOf:
- type: string
- type: 'null'
title: Site Id
description: The ID of the SharePoint site to download from.
folder_path:
anyOf:
- type: string
- type: 'null'
title: Folder Path
description: The path of the Sharepoint folder to read from.
folder_id:
anyOf:
- type: string
- type: 'null'
title: Folder Id
description: The ID of the Sharepoint folder to read from.
drive_name:
anyOf:
- type: string
- type: 'null'
title: Drive Name
description: The name of the Sharepoint drive to read from.
client_id:
type: string
title: Client Id
description: The client ID to use for authentication.
client_secret:
type: string
format: password
title: Client Secret
description: The client secret to use for authentication.
writeOnly: true
tenant_id:
type: string
title: Tenant Id
description: The tenant ID to use for authentication.
required_exts:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Required Exts
description: The list of required file extensions.
get_permissions:
type: boolean
title: Get Permissions
description: Whether to get permissions for the sharepoint site.
default: true
include_path_patterns:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Include Path Patterns
description: 'List of regex patterns for file paths to include. Full paths (including filename) must match at least one pattern to be included. Example: [''/reports/'', ''/docs/.*\.pdf$'', ''^Report.*\.pdf$'']'
exclude_path_patterns:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Exclude Path Patterns
description: 'List of regex patterns for file paths to exclude. Files whose paths (including filename) match any pattern will be excluded. Example: [''/temp/'', ''/backup/'', ''\.git/'', ''\.tmp$'', ''^~'']'
class_name:
type: string
title: Class Name
default: CloudSharepointDataSource
type: object
required:
- client_id
- client_secret
- tenant_id
title: CloudSharepointDataSource
CloudJiraDataSourceV2:
properties:
supports_access_control:
type: boolean
title: Supports Access Control
default: false
email:
anyOf:
- type: string
- type: 'null'
title: Email
description: The email address to use for authentication.
api_token:
anyOf:
- type: string
format: password
writeOnly: true
- type: 'null'
title: Api Token
description: The API Access Token used for Basic, PAT and OAuth2 authentication.
server_url:
type: string
title: Server Url
description: The server url for Jira Cloud.
cloud_id:
anyOf:
- type: string
- type: 'null'
title: Cloud Id
description: The cloud ID, used in case of OAuth2.
authentication_mechanism:
type: string
title: Authentication Mechanism
description: Type of Authentication for connecting to Jira APIs.
api_version:
type: string
enum:
- '2'
- '3'
title: Api Version
description: Jira REST API version to use (2 or 3). 3 supports Atlassian Document Format (ADF).
default: '2'
query:
type: string
title: Query
description: JQL (Jira Query Language) query to search.
fields:
anyOf:
- items:
type: string
type: array
- type: 'null'
title: Fields
description: List of fields to retrieve from Jira. If None, retrieves all fields.
expand:
anyOf:
- type: string
- type: 'null'
title: Expand
description: Fields to expand in the response.
requests_per_minute:
anyOf:
- type: integer
- type: 'null'
title: Requests Per Minute
description: Rate limit for Jira API requests per minute.
get_permissions:
type: boolean
title: Get Permissions
description: Wh
# --- truncated at 32 KB (33 KB total) ---
# Full source: https://raw.githubusercontent.com/api-evangelist/llamaparse/refs/heads/main/openapi/llamaparse-data-sources-api-openapi.yml